Take the events off a map

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds non-annotated behavior: the whole removal happens 'in one transaction' (atomicity), dryRun returns a preview rather than mutating, and the map is rendered in the reply. It does not discuss undo/rollback paths despite undo_writes and rollback_data existing as siblings.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded in the first sentence, and each following sentence adds distinct information (rationale, dryRun, return rendering). The rebuild-script narrative is slightly padded, but nothing is repeated and no sentence is pure filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description usefully states that the map is rendered in the reply and that dryRun returns a preview, and it covers atomicity and filtering. Remaining gaps are edge cases: invalid mapId behavior, filter combination rules, and whether the clear is recoverable via the rollback/undo siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%; mapId and dryRun have no schema descriptions at all. The description compensates by explaining dryRun ('answers with what would go') and by describing the filter semantics (by name, by character sheet, or all), which is more than the schema conveys. It still doesn't clarify how multiple filters combine (AND vs OR) or what eventId does when combined with name/characterName.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource with scope: 'Remove every event on a map in one transaction, or only the ones whose name or character sheet you name.' It is immediately distinguishable from the sibling remove_event (single-event) and find_events (query-only), without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly frames the use case against the alternative: without this call a rebuild means 'one remove_event per event and a half-finished map if the script dies halfway.' It also routes the inspection case to dryRun ('the quickest way to see a map's cast'), so both the do-this and do-that-instead paths are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.